Kanghoon Lee

A Hybrid Approach of Imitation Learning and Deep Reinforcement Learning with Direct-Effect Update Interval for Elevator Dispatching

Jiansong Wan, Kanghoon Lee, Hayong Shin

The rapid increase in high-rise building construction has intensified the need for efficient elevator system operations. This article addresses the elevator dispatching problem in elevator group control systems. We formulate the problem as a Semi-Markov Decision Process (SMDP), defining the state representation, …

kr (code pays fourni par la source)

Priority-Aware Multi-Robot Coverage Path Planning

Kanghoon Lee, H Kim, J Li, J. H. Park

Multi-robot systems are widely used for coverage tasks that require efficient coordination across large environments. In Multi-Robot Coverage Path Planning (MCPP), the objective is typically to minimize the makespan by generating non-overlapping paths for full-area coverage. However, most existing methods assume uniform …

kr, us (code pays fourni par la source)

Analysis of Family Center Evaluation Results through Keyword Network Analysis

Kyoungeun Kim, Bogchong Kang, Ocknyu Kim, Kanghoon Lee et autres

The purpose of this study is to explore alternatives to improve the evaluation guidelines of the family center by conducting a keyword network analysis based on the evaluation results of the family center. For this study, 200 keywords were extracted through the …

Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm

Hyeon-Jun Kim, Kanghoon Lee, Junho Park, Jiachen Li et autres

Multi-Agent Reinforcement Learning (MARL) has shown promise in solving complex problems involving cooperation and competition among agents, such as an Unmanned Surface Vehicle (USV) swarm used in search and rescue, surveillance, and vessel protection. However, aligning system behavior with user preferences is …

kr, us (code pays fourni par la source)

Phosphorus removal from aqueous solutions using hematite-coated expanded graphite: Isotherm modeling and thermodynamic insights

Myungchan Kim, Kanghoon Lee, Duksoo Jang, Sung-Ju Im

Hematite-coated expanded graphite, a newly developed nanocomposite, has demonstrated high efficiency as an adsorbent for the removal of various metal ions and inorganic contaminants from aqueous solutions. To enhance its durability and adsorption performance, hematite nanoparticles were synthesized onto expanded graphite, and …

TrajEvo: Designing Trajectory Prediction Heuristics via LLM-driven Evolution

Zhikai Zhao, Chuanbo Hua, Federico Berto, Kanghoon Lee et autres

Trajectory prediction is a crucial task in modeling human behavior, especially in fields as social robotics and autonomous vehicle navigation. Traditional heuristics based on handcrafted rules often lack accuracy, while recently proposed deep learning approaches suffer from computational cost, lack of explainability, …

Hierarchical Decomposition Framework for Steiner Tree Packing Problem

Hanbum Ko, Minu Kim, Han-Seul Jeong, Sunghoon Hong et autres

kr, us (code pays fourni par la source)

Measurement and validity study on police effectiveness

Jaehoon Jung, Kanghoon Lee, 김소영

The purpose of this study is to identify and validate how police effectiveness, one of the key variables in procedural justice theory, is measured. Police effectiveness is an instrumental measure of whether the police are successful in deterring and solving crime, and …

ELA: Exploited Level Augmentation for Offline Learning in Zero-Sum Games

Shiqi Lei, Kanghoon Lee, Linjing Li, J. H. Park et autres

Offline learning derives effective policies from expert demonstrators' datasets without direct interaction. While recent research consider dataset characteristics like expertise level or multiple demonstrators, a distinct approach is necessary in zero-sum games, where outcomes significantly depend on the opponent's strategy. In this …

cn, kr, us (code pays fourni par la source)

Naphtha Cracking Center Scheduling Optimization using Multi-Agent Reinforcement Learning

Sunghoon Hong, Deunsol Yoon, Whiyoung Jung, Jinsang Lee et autres

The Naphtha Cracking Center (NCC) is central to petrochemical feedstock production through the intricate process. It consists of receipt stage for unloading naphtha, blending stage for mixing naphtha, and furnace stage for producing marketable products. It is crucial to make an optimal …

us, kr (code pays fourni par la source)

A Validity Study of Depression Scale among the Probation Officers

Heekyun Park, Kanghoon Lee, Jaehoon Jung

보호직공무원은 업무 과중과 인력 부족 현상을 겪고 있다. 이러한 환경은 보호직공무원의 우울을 유발할 수 있으며, 이들이 우울을 경험하게 된다면 결국 ‘범죄 없는 밝고 건강한 사회구현’이라는 조직의 비전 달성을 어렵게 만들 것이다. 경찰·해양경찰공무원, 소방공무원 등을 대상으로 우울증에 관한 연구가 다수 진행되고 있지만, 보호직공무원을 …

Interactive Autonomous Navigation with Internal State Inference and Interactivity Estimation

Jiachen Li, David Isele, Kanghoon Lee, Jinkyoo Park et autres

Deep reinforcement learning (DRL) provides a promising way for intelligent agents (e.g., autonomous vehicles) to learn to navigate complex scenarios. However, DRL with neural networks as function approximators is typically considered a black box with little explainability and often suffers from suboptimal …